EMOTHAW: A novel database for emotional state recognition from handwriting

TL;DR

This paper introduces EMOTHAW, a new publicly available handwriting database linking emotional states like anxiety, depression, and stress to handwriting features, and demonstrates classification of these states with up to 71% accuracy.

Contribution

The paper presents the first handwriting database annotated with emotional states and applies machine learning to classify emotions from handwriting features.

Findings

Emotional states can be classified from handwriting with 60-71% accuracy.

Features related to timing and ductus are effective for emotion recognition.

The database enables future research in emotion detection via handwriting.

Abstract

The detection of negative emotions through daily activities such as handwriting is useful for promoting well-being. The spread of human-machine interfaces such as tablets makes the collection of handwriting samples easier. In this context, we present a first publicly available handwriting database which relates emotional states to handwriting, that we call EMOTHAW. This database includes samples of 129 participants whose emotional states, namely anxiety, depression and stress, are assessed by the Depression Anxiety Stress Scales (DASS) questionnaire. Seven tasks are recorded through a digitizing tablet: pentagons and house drawing, words copied in handprint, circles and clock drawing, and one sentence copied in cursive writing. Records consist in pen positions, on-paper and in-air, time stamp, pressure, pen azimuth and altitude. We report our analysis on this database. From collected data, we first compute measurements related to timing and ductus. We compute separate measurements according to the position of the writing device: on paper or in-air. We analyse and classify this set of measurements (referred to as features) using a random forest approach. This latter is a machine learning method [2], based on an ensemble of decision trees, which includes a feature ranking process. We use this ranking process to identify the features which best reveal a targeted emotional state. We then build random forest classifiers associated to each emotional state. Our results, obtained from cross-validation experiments, show that the targeted emotional states can be identified with accuracies ranging from 60% to 71%.